Interview Questions › AI Product

Conversational shopping assistant

Flipkart wants a chat assistant that helps shoppers decide what to buy, for example "a phone under ₹20,000 with a good camera". Design it and decide how to measure it.

Context

Many users are first-time online shoppers and use regional languages. Sellers pay for ads and want visibility.

Clarifying questions to ask first

• Which categories first?
• Can sponsored products appear in answers?
• Which languages?

How to approach it

1. Start from the user problem, not the model: is AI the right tool here?
2. Describe the experience and where the model fits in it
3. Define what "good output" means and how you would evaluate it before and after launch
4. Name the failure modes (wrong answers, bias, privacy, cost) and how you contain them
5. Close with a launch plan and success metrics

Framework: User and problem -> Is AI the right tool? -> Experience design and human-in-the-loop -> Quality bar and evaluation -> Risks, cost and latency -> Staged launch and metrics

Sample answer

• Ground in catalogue and reviews, show specs side by side
• Label sponsored items clearly
• Measure regret (returns), not just conversion

1. Eval of spec accuracy against catalogue
2. Assisted vs unassisted conversion in an A/B test
3. Returns for "not as expected" as the regret metric

Start with phones and appliances in Hindi and English, ground every claim in catalogue data, and label sponsored results. Success is assisted conversion with returns for "not as expected" flat or lower.

What interviewers look for

• Assisted conversion
• Return rate
• Answer accuracy